This Author published in this journals
All Journal Technomedia Journal
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Implementasi CNN dan MediaPipe dalam Peningkatan Efektivitas Stretching pada Olahraga Futsal: Implementation of CNN and MediaPipe in Increasing the Effectiveness of Stretching in Futsal Sports Jericho, Vito; Rochadiani, Theresia Herlina
Technomedia Journal Vol 9 No 3 (2025): February
Publisher : Pandawan Incorporation, Alphabet Incubator Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/tmj.v9i3.2294

Abstract

This study aims to develop an effective Convolutional Neural Network (CNN) model in recognizing stretchingmovements that are often performed by futsal players, with the aim of reducing the risk of injury. The dataset usedconsists of 3000 images covering five types of movements: High Knees, Jumping Jacks, Lunge, Side Lunge, and ButtKicks. The data was taken from YouTube videos and processed to produce landmarks through MediaPipe technology. The CNN model was trained using the ”Adam” optimizer, with 50 epochs, a batch size of 8, and a learning rate of 0.001. The training results showed an accuracy of 94%, with the best performance on the Lunge and Jumping Jack movements, and adequate performance on other movements. The implementation of this model allows real-time monitoring of stretching movements, provides direct feedback to users, and helps futsal players in stretching with the right technique to avoid injury. This study shows that the CNN-based approach for stretching motion recognition in futsal is effective and reliable. Furtherresearch is suggested to increase the amount of training data and explore different model architectures to strengthen the model’s generalization.